Events Calendar

NL Seminar- Weakly Supervised Learning for Adaptive LLM Agents

Speaker: Da Yin, UCLA

Talk Title: Weakly Supervised Learning for Adaptive LLM Agents

Abstract: REMINDER: Meeting hosts only admit on-line guests that they know to the Zoom meeting. Hence, you’re highly encouraged to use your USC account to sign into Zoom. If you’re an outside visitor, please inform us at (nlg-seminar-host(at)isi.edu) to make us aware of your attendance so we can admit you. Specify if you will attend remotely or in person at least one business day prior to the event  Provide your: full name, job title and professional affiliation and arrive at least 10 minutes before the seminar begins. If you do not have access to the 6th Floor for in-person attendance, please check in at the 10th floor main reception desk to register as a visitor and someone will escort you to the conference room location. ZOOM INFO: https://usc.zoom.us/j/98977559622?pwd=IK59VbdZJiGIPV9xjUjabrjEauRDai.1 Meeting ID: 989 7755 9622 Passcode: 307452 LLM agents are revolutionizing complex task-solving through multi-step planning, reasoning, and real-world or simulated interactions. However, their adaptability to unseen tasks and environments remains a challenge, especially with limited training resources. In this talk, I will first introduce Agent Lumos (ACL 2024), a foundational framework for training general-purpose, open-source LLM agents that enables better generalization across domains, by the unified training over the trajectories converted from the ubiquitous, unstructured annotated reasoning rationales. I will also discuss Trial and Error (ACL 2024) and Q* Agent, which foster self-exploration, and collect trajectories for preference optimization and process reward modeling based on environmental feedback. Finally, I will outline future directions, including agent critique and world models, to enhance LLM adaptability with minimal effort.

Biography: Da Yin is a final-year PhD student in Computer Science at UCLA, advised by Prof. Kai-Wei Chang, working in the UCLA NLP lab. He was awarded Amazon PhD Fellowship and Best Paper Award at EMNLP Pan-DL workshop in 2023. He was also the co-organizer of 1st ACL MML workshop, publicity chair of 4th SocalNLP Symposium, and area chair at ACL ARR from 2023. His research interest is building generalizable, adaptive, and inclusive language processing models that can be applied across applications and regions.

Host: Jonathan May and Katy Felkner

More Info: https://www.isi.edu/research-groups-nlg/nlg-seminars/

Webcast: https://www.youtube.com/watch?v=dT-Gaolql1c

Location: Information Science Institute (ISI) - Conf Rm#689

WebCast Link: https://www.youtube.com/watch?v=dT-Gaolql1c

Audiences: Everyone Is Invited

Contact: Pete Zamar

Event Link: https://www.isi.edu/research-groups-nlg/nlg-seminars/